Diagnose slow loading, high memory use, and low frame rates in USD 3D scenes. Coordinate scene structure checks, validation, optimization, and before-and-after performance comparisons, then produce a report documenting findings and changes.
Update copies of public-company Excel models using financial disclosures and mapped input cells. Deliver an updated workbook or review workbook, with source references, change logs, unresolved items, and implications for estimates and valuation where the model supports them.
Configure how Dynamo routes requests to workers, then check model discovery and a chat response. Supports local and Kubernetes setups, including routing based on cached model data, with clear commands, results, and limitations.
Coordinate CAD and source assets through conversion to USD, a 3D scene format, material and physics assignment, and SimReady checks. Produce stage reports, with preview rendering and validated delivery packages when requested.
Evaluate local Codex skills and plugins, understand their scores, and identify fixes to prioritize. Get explanations of token estimates, set up benchmark scenarios, and prepare workflows for measuring actual token usage.
Create concise, source-backed profiles of public companies, covering business drivers, key metrics, valuation context, and risks. Identify stale or missing evidence and distinguish reported facts from estimates to provide a baseline for further investment research.
Compares a prototype’s rendered screens with its source design to find differences in typography, spacing, colors, images, and text. Produces prioritized fixes and records visual evidence from follow-up checks before handoff.
Deploy a runnable prototype to the hosting service you choose, such as Sites or Vercel. Use the available deployment tool, return a working shareable URL, and identify any remaining manual steps.
Add team-specific evaluation criteria to plugin-eval by designing a metric pack, a set of custom checks and measurements. Create its manifest and JSON-producing script, then run it through the evaluator using a consistent output structure.
Compare a listed company with relevant peers using valuation multiples, ratios linking price or company value to financial measures. Produce reports or editable workbooks covering peer selection, implied prices, data quality, and valuation assumptions.
Audit existing public equity investment models and spreadsheets for formula errors, source support, assumptions, and scenario quality. Receive a readiness verdict, an issue log, and prioritized fixes showing whether the model supports its intended decision.
Build, refactor, and troubleshoot ChatGPT apps with an MCP server, which exposes tools to the assistant, and an interactive widget. Use official documentation and examples to plan tools, scaffold code, configure security settings, and validate local operation.
Analyze public-company earnings after results are released, combining reported figures, guidance, estimates, and call evidence. Produces source-backed reports that examine recurring profitability, investment implications, key business drivers, and upcoming events to monitor.
Analyze how changing assumptions affects an existing public-equity model or investment thesis. Build scenarios and sensitivity tables, identify where the thesis breaks, and define evidence or thresholds that would change an investment decision.
Set up NVIDIA infrastructure for synthetic data generation on MicroK8s or Azure AKS. Coordinate Kubernetes, inference services, and OSMO workflow execution, with prerequisite checks, deployment validation, capacity planning, and failure investigation before workloads are retried.
Turn a product design brief and visual references into three distinct design images. Compare layouts, information priorities, and interaction approaches, then refine or combine ideas to choose a visual direction before implementation begins.
Clarify what a product interface should be and what users should accomplish before design or prototyping begins. Ask only about missing information, summarize the brief and assumptions, then continue into the appropriate design workflow.
Evaluate a local Codex plugin to understand its scores and identify what to fix first. Review stronger and weaker skills, prepare benchmark runs, compare saved results across versions, and produce a readable report.
Turn an idea, existing code, or a previous Codex conversation into a runnable OpenAI Agents SDK app. Supports local verification, focused evaluations of agent behavior, and local deployment through the Deployment Manager.
Routes listed-company investment research to specialist skills for earnings analysis, valuation, financial model updates, and portfolio risk reviews. Helps organize evidence, assumptions, and investment theses into reports, models, memos, and monitoring trackers.
Research current user problems with a named digital product using public sources and permitted internal sources. Group evidence into usability issues, rank their importance, and produce a concise brief with citations and recommended improvements.
Analyze product usage in PostHog and manage experiments, dashboards, surveys, and feature flags, which control feature availability. Use connected tools to investigate user behavior and errors, run queries, and summarize findings with numbers and links.
Save and manage product references and design preferences for future Product Design work. Keep product URLs, Figma files, screenshots, brand assets, and other context available, and review or update what has already been saved.
Diagnose failed OpenAI API requests by separating network problems, authentication errors, exhausted credits, rate limits, and access restrictions. Use concrete error messages to explain the likely cause and direct users to the appropriate next action.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)